Mercurial > repos > proteore > proteore_ms_observation_pepatlas

comparison Get_ms-ms_observations.R @ 2:6ab9d2778f04 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload commit bdd7e8a1f08c11db2a9f1b6db5535c6d32153b2b
author proteore
date Tue, 18 Dec 2018 09:50:50 -0500
parents
children e77c0f3e9bab
comparison
equal deleted inserted replaced
1:23671dd35026 2:6ab9d2778f04
1 # Read file and return file content as data.frame
2 read_file <- function(path,header){
3 file <- try(read.csv(path,header=header, sep="\t",stringsAsFactors = FALSE, quote="\"", check.names = F),silent=TRUE)
4 if (inherits(file,"try-error")){
5 stop("File not found !")
6 }else{
7 return(file)
8 }
9 }
10
11 str2bool <- function(x){
12 if (any(is.element(c("t","true"),tolower(x)))){
13 return (TRUE)
14 }else if (any(is.element(c("f","false"),tolower(x)))){
15 return (FALSE)
16 }else{
17 return(NULL)
18 }
19 }
20
21 nb_obs_PeptideAtlas <- function(input, atlas_file) {
22 ## Calculate the sum of n_observations for each ID in input
23 atlas = read_file(atlas_file, T)
24 return(atlas$nb_obs[match(input,atlas$Uniprot_AC)])
25 }
26
27 main = function() {
28 args <- commandArgs(TRUE)
29 if(length(args)<1) {
30 args <- c("--help")
31 }
32
33 # Help section
34 if("--help" %in% args) {
35 cat("Selection and Annotation HPA
36 Arguments:
37 --input_type: type of input (list of id or filename)
38 --input: input
39 --atlas: list of file(s) path to use
40 --output: text output filename \n")
41 q(save="no")
42 }
43
44 # Parse arguments
45 parseArgs <- function(x) strsplit(sub("^--", "", x), "=")
46 argsDF <- as.data.frame(do.call("rbind", parseArgs(args)))
47 args <- as.list(as.character(argsDF$V2))
48 names(args) <- argsDF$V1
49
50 #save(args,file="/home/dchristiany/proteore_project/ProteoRE/tools/retrieve_msbased_pepatlas/args.Rda")
51 #load("/home/dchristiany/proteore_project/ProteoRE/tools/retrieve_msbased_pepatlas/args.Rda")
52
53 # Extract input
54 input_type = args$input_type
55 if (input_type == "list") {
56 input = strsplit(args$input, "[ \t\n]+")[[1]]
57 } else if (input_type == "file") {
58 filename = args$input
59 ncol = args$column
60 # Check ncol
61 if (! as.numeric(gsub("c", "", ncol)) %% 1 == 0) {
62 stop("Please enter an integer for level")
63 } else {
64 ncol = as.numeric(gsub("c", "", ncol))
65 }
66 header = str2bool(args$header)
67 file = read_file(filename, header)
68 input = sapply(file[,ncol],function(x) strsplit(as.character(x),";")[[1]][1],USE.NAMES = F)
69 }
70
71 output = args$output
72
73 #function to create a list of infos from file path
74 extract_info_from_path <- function(path) {
75 file_name=strsplit(tail(strsplit(path,"/")[[1]],n=1),"\\.")[[1]][1]
76 date=tail(strsplit(file_name,"_")[[1]],n=1)
77 tissue=paste(strsplit(file_name,"_")[[1]][1:2],collapse="_")
78 return (c(date,tissue,file_name,path))
79 }
80
81 #data_frame building
82 paths=strsplit(args$atlas,",")[[1]]
83 tmp <- sapply(paths, extract_info_from_path,USE.NAMES = FALSE)
84 df <- as.data.frame(t(as.data.frame(tmp)),row.names = c(""),stringsAsFactors = FALSE)
85 names(df) <- c("date","tissue","filename","path")
86
87 # Annotations
88 res = sapply(df$path, function(x) nb_obs_PeptideAtlas(input, x), USE.NAMES = FALSE)
89
90 colnames(res)=df$filename
91
92 # Write output
93 if (input_type == "list") {
94 res = cbind(as.matrix(input), res)
95 colnames(res)[1] = "Uniprot accession number"
96 } else if (input_type == "file") {
97 res = cbind(file, res)
98 }
99 res = as.data.frame(apply(res, c(1,2), function(x) gsub("^$|^ $", NA, x)))
100 write.table(res, output, row.names = FALSE, sep = "\t", quote = FALSE)
101
102 }
103
104 main()
105 #Rscript retrieve_peptideatlas.R --input_type="file" --input="test-data/FKW_Lacombe_et_al_2017_OK.txt" --atlas_brain="Human_Brain_201803_PeptideAtlas.txt" --column="c1" --header="true" --output="test-data/PeptideAtlas_output.txt" --atlas_urine="Human_Urine_201803_PeptideAtlas.txt" --atlas="brain,urine"
106